# AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images

arXiv: https://arxiv.org/abs/2201.05344 · HTML: https://mlsanity.com/paper/2201.05344/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 87 references that are in the map.
- First posted on arXiv 14 Jan 2022.

## Builds on (most cited first, 27 of 27)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation](https://mlsanity.com/paper/1809.10486/) (2018)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [Multivariate mixture model for myocardium segmentation combining multi-source images](https://mlsanity.com/paper/1612.08820/) (2016)
- [CentralNet: a Multilayer Approach for Multimodal Fusion](https://mlsanity.com/paper/1808.07275/) (2018)
- [Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks](https://mlsanity.com/paper/1808.08127/) (2018)
- [DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding](https://mlsanity.com/paper/1709.04696/) (2017)
- [The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1704.01664/) (2017)
- [Simulation of hyperelastic materials in real-time using Deep Learning](https://mlsanity.com/paper/1904.06197/) (2019)
- [AM-LFS: AutoML for Loss Function Search](https://mlsanity.com/paper/1905.07375/) (2019)
- [Object Detection from Scratch with Deep Supervision](https://mlsanity.com/paper/1809.09294/) (2018)
- [Atrial Scar Quantification via Multi-scale CNN in the Graph-cuts Framework](https://mlsanity.com/paper/1902.07877/) (2019)
- [Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention](https://mlsanity.com/paper/2006.13011/) (2020)
- [Cardiac MRI Segmentation with Strong Anatomical Guarantees](https://mlsanity.com/paper/1907.02865/) (2019)
- [Enhanced detection of fetal pose in 3D MRI by Deep Reinforcement Learning with physical structure priors on anatomy](https://mlsanity.com/paper/2007.08146/) (2020)
- [Auto-weighting for Breast Cancer Classification in Multimodal Ultrasound](https://mlsanity.com/paper/2008.03435/) (2020)
- [Multiview Two-Task Recursive Attention Model for Left Atrium and Atrial Scars Segmentation](https://mlsanity.com/paper/1806.04597/) (2018)
- [Automatic Segmentation of Gross Target Volume of Nasopharynx Cancer using Ensemble of Multiscale Deep Neural Networks with Spatial Attention](https://mlsanity.com/paper/2101.11254/) (2021)
- [Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images](https://mlsanity.com/paper/2008.05780/) (2020)

## Built on by (most cited first, 10 of 10)

- [MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images](https://mlsanity.com/paper/2211.03062/) (2022)
- [Multi-Modality Cardiac Image Computing: A Survey](https://mlsanity.com/paper/2208.12881/) (2022)
- [Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference](https://mlsanity.com/paper/2307.04421/) (2023)
- [Attention Mechanisms in Medical Image Segmentation: A Survey](https://mlsanity.com/paper/2305.17937/) (2023)
- [Aligning Multi-Sequence CMR Towards Fully Automated Myocardial Pathology Segmentation](https://mlsanity.com/paper/2302.03537/) (2023)
- [AATCT-IDS: A Benchmark Abdominal Adipose Tissue CT Image Dataset for Image Denoising, Semantic Segmentation, and Radiomics Evaluation](https://mlsanity.com/paper/2308.08172/) (2023)
- [CANet: Channel Extending and Axial Attention Catching Network for Multi-structure Kidney Segmentation](https://mlsanity.com/paper/2208.05241/) (2022)
- [Subtyping Breast Lesions via Generative Augmentation based Long-tailed Recognition in Ultrasound](https://mlsanity.com/paper/2507.22568/) (2025)
- [Automated Diagnosis of Cardiovascular Diseases from Cardiac Magnetic Resonance Imaging Using Deep Learning Models: A Review](https://mlsanity.com/paper/2210.14909/) (2022)
- [Do Not Break the Vessels: Structure-Preserving Mean Flow for Vascular Image Translation](https://mlsanity.com/paper/2606.31095/) (2026)

## Abstract (arXiv)

Multi-sequence cardiac magnetic resonance (CMR) provides essential pathology information (scar and edema) to diagnose myocardial infarction. However, automatic pathology segmentation can be challenging due to the difficulty of effectively exploring the underlying information from the multi-sequence CMR data. This paper aims to tackle the scar and edema segmentation from multi-sequence CMR with a novel auto-weighted supervision framework, where the interactions among different supervised layers are explored under a task-specific objective using reinforcement learning. Furthermore, we design a coarse-to-fine framework to boost the small myocardial pathology region segmentation with shape prior knowledge. The coarse segmentation model identifies the left ventricle myocardial structure as a shape prior, while the fine segmentation model integrates a pixel-wise attention strategy with an auto-weighted supervision model to learn and extract salient pathological structures from the multi-sequence CMR data. Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods. Our method is promising in advancing the myocardial pathology assessment on multi-sequence CMR data. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/AWSnet/tree/master.